当前位置: X-MOL 学术Pattern Recogn. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Dynamic sampling for deep metric learning
Pattern Recognition Letters ( IF 5.1 ) Pub Date : 2021-07-21 , DOI: 10.1016/j.patrec.2021.06.027
Chang-Hui Liang 1 , Wan-Lei Zhao 1 , Run-Qing Chen 1
Affiliation  

Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold. The learning process is mainly based on the supplied image negative and positive training pairs. In this paper, a dynamic sampling strategy is proposed to organize the training pairs in an easy-to-hard order to feed into the network. It allows the network to learn general boundaries between categories from the easy training pairs at its early stages and finalize the details of the model mainly relying on the hard training samples in the later. Compared to the existing training sample mining approaches, the hard samples are mined with little harm to the learned general model. This dynamic sampling strategy is formulated as two simple terms that are compatible with various loss functions. Consistent performance boost is observed when it is integrated with several popular loss functions on fashion search and fine-grained image search.



中文翻译:

深度度量学习的动态采样

深度度量学习将视觉上相似的图像映射到附近的位置,并将视觉上不同的图像映射到嵌入流形中。学习过程主要基于提供的图像负和正训练对。在本文中,提出了一种动态采样策略,以从易到难的顺序组织训练对以输入网络。它允许网络在早期阶段从简单的训练对中学习类别之间的一般边界,并在后期主要依靠硬训练样本来确定模型的细节。与现有的训练样本挖掘方法相比,硬样本的挖掘对学习到的通用模型的危害很小。这种动态采样策略被表述为两个与各种损失函数兼容的简单术语。

更新日期:2021-07-29
down
wechat
bug